def fitSkewedNormal(rand, ax, label, alpha_hist=0.4, color_line='r'):
ax.set_title(label, fontsize=18)
param = stats.skewnorm.fit(rand)
x_rand, p_rand = getDistribution(rand)
pdf_fitted = stats.skewnorm.pdf(x_rand,
param[0],
loc=param[1],
scale=param[2])
mean = stats.skewnorm.mean(param[0], loc=param[1], scale=param[2])
maxx = x_rand[pdf_fitted.tolist().index(max(pdf_fitted))]
counts, bins, bars = ax.hist(rand,
normed=True,
bins=np.linspace(min(x_rand), max(x_rand),
25),
alpha=alpha_hist)
sk_results_norm = stats.kstest(
np.asarray(pdf_fitted), lambda x: stats.skewnorm.cdf(
x_rand, param[0], loc=param[1], scale=param[
2])) # stats.ks_2samp(np.cumsum(p_rand), np.cumsu
ax.plot(x_rand,
pdf_fitted,
'-',
color=color_line,
linewidth=3,
label='$\\mu$=' + str(round(mean, 2)) + ', $\\mu^{*}$=' +
str(maxx) + '\n$D$=' + str(round(sk_results_norm[0], 2)) +
', $p$=' + str(round(sk_results_norm[1], 2)))
return mean, sk_results_norm[0], sk_results_norm[1], param[0], param[
1], param[2]
def fitPowerLaw(rand, ax, label):
ax.set_title(label, fontsize=18)
# histogram
print 'Fitting lognormal...'
x_rand, p_rand = getDistribution(rand)
counts, bins, bars = ax.hist(
rand,
normed=True,
bins=10**np.linspace(np.log10(min(x_rand)), np.log10(max(x_rand)), 15),
log=True,
alpha=0.0) #, histtype='step', linewidth = 0)
ax.plot((bins[1:] + bins[:-1]) / 2,
counts,
's-',
color='royalblue',
alpha=0.5,
markersize=12,
linewidth=2)
# get the lognormal
param = stats.lognorm.fit(rand)
pdf_fitted = stats.lognorm.pdf(x_rand,
param[0],
loc=param[1],
scale=param[2]) #
mu = np.log(param[2])
sigma = param[0]
sk_results_norm = stats.kstest(
np.asarray(pdf_fitted), lambda x: stats.lognorm.cdf(
x_rand, param[0], loc=param[1], scale=param[
2])) # stats.ks_2samp(np.cumsum(p_rand), np.cumsu
ax.plot(x_rand,
pdf_fitted,
'k-',
linewidth=4,
label='$\\mu$=' + str(round(mu, 2)) + ' $\\sigma$=' +
str(round(sigma, 2)) + ', $D$=' +
str(round(sk_results_norm[0], 2)))
# fit and plot the powerlaw
results = powerlaw.Fit(rand, xmin=min(x_rand), fit_method='KS')
alpha = results.power_law.alpha
xmin = results.power_law.xmin
D = results.power_law.KS()
results.power_law.plot_pdf(color='r',
ax=ax,
linestyle='-',
linewidth=4,
label='$\\alpha$= ' + str(round(alpha, 2)) +
', $x_{min}$=' + str(round(xmin, 2)) +
'\n$D$=' + str(round(D, 2)))
ax.set_ylim([min(counts), 1.1])
ax.set_xlim([min(x_rand), max(bins)])
return alpha, xmin, D
def plot_exponent(series, ax, num_of_bins, color, label):
x_series, p_series = getDistribution(series, True)
bx_series, bp_series, bp_series_err = getBinnedDistribution(
x_series, p_series, num_of_bins)
ax.plot(x_series, p_series, color + 'o', alpha=0.1, markersize=7)
ax.errorbar((bx_series[1:] + bx_series[:-1]) / 2,
bp_series,
yerr=bp_series_err,
color=color,
fmt='o-',
alpha=0.9,
capsize=3,
elinewidth=1,
linewidth=3,
label=label)
def fitPowerLaw(rand, ax, label):
ax.set_title(label, fontsize=18)
# get the scatterplot
x_rand, p_rand = getDistribution(rand)
# fit and plot the lognormal
print 'Fitting lognormal...'
counts, bins, bars = ax.hist(
rand,
normed=True,
bins=10**np.linspace(np.log10(min(x_rand)), np.log10(max(x_rand)), 15),
log=True,
alpha=0.0) #, histtype='step', linewidth = 0)
ax.plot((bins[1:] + bins[:-1]) / 2,
counts,
's-',
color='royalblue',
alpha=0.5,
markersize=12,
linewidth=2)
# fit and plot the powerlaw
results = powerlaw.Fit(rand, xmin=min(x_rand), fit_method='KS')
alpha = results.power_law.alpha
xmin = results.power_law.xmin
D = results.power_law.KS()
results.power_law.plot_pdf(marker='o',
color='r',
ax=ax,
linestyle='-',
linewidth=3,
label='$\\alpha$= ' + str(round(alpha, 2)) +
', $x_{min}$=' + str(round(xmin, 2)) +
'\n$D$=' + str(round(D, 2)))
ax.set_ylim([min(counts), 1.1])
ax.set_xlim([min(x_rand), max(bins)])
return alpha, xmin, D
def fitSkewedNormal(filename, ax, label, alpha_hist=0.2, color_line='r'):
rand = np.asarray([float(line.strip()) for line in open(filename)])
print 'Fitting normal...'
param = stats.skewnorm.fit(rand)
x_rand, p_rand = getDistribution(rand)
pdf_fitted = stats.skewnorm.pdf(x_rand,
param[0],
loc=param[1],
scale=param[2])
mean = stats.skewnorm.mean(param[0], loc=param[1], scale=param[2])
maxx = str(x_rand[pdf_fitted.tolist().index(max(pdf_fitted))])
counts, bins, bars = ax.hist(rand,
bins=np.linspace(min(x_rand), max(x_rand),
25),
normed=True,
alpha=alpha_hist)
sk_results = stats.kstest(
np.asarray(pdf_fitted), lambda x: stats.skewnorm.cdf(
x_rand, param[0], loc=param[1], scale=param[2]))
ax.plot(x_rand,
pdf_fitted,
'-',
color=color_line,
linewidth=3,
label='$\\mu$=' + str(round(mean, 2)) + ', $\\mu^{*}$=' + maxx +
'\n$D$=' + str(round(sk_results[0], 2)) + ', $p$=' +
str(round(sk_results[1], 2)))
ax.set_title(label, fontsize=18)
ax.set_yticks(np.linspace(0, max(counts), 5))
ax.set_yticklabels([
str(int(100 * y)) + '%'
for y in np.linspace(0, 1.05 * max(counts) / (sum(counts)), 5)
])
def fitAndStatsTransformedNormal(filename,
ax,
label,
outfolder,
name,
statfile,
filterparam,
alpha_hist=0.2,
color_line='r'):
if 'log_Q' in name:
rand = np.asarray([
float(line.strip().split('\t')[1]) for line in open(filename)
if len(line.strip().split('\t')) > 1
])
else:
rand = np.asarray([float(line.strip()) for line in open(filename)])
mmin = min(rand)
rand = [math.log(rr - mmin + 1) for rr in rand]
print 'Fitting normal...'
param = stats.norm.fit(rand)
print param
x_rand, p_rand = getDistribution(rand)
pdf_fitted = stats.norm.pdf(x_rand, loc=param[0], scale=param[1])
mean, variance = stats.norm.stats(loc=param[0],
scale=param[1],
moments='mv')
maxx = x_rand[pdf_fitted.tolist().index(max(pdf_fitted))]
counts, bins, bars = ax.hist(rand,
bins=np.linspace(min(x_rand), max(x_rand),
25),
normed=True,
alpha=alpha_hist)
D = stats.kstest(
np.asarray(pdf_fitted),
lambda x: stats.norm.cdf(x_rand, loc=param[0], scale=param[1]))[0]
counts, bins, bars = ax.hist(rand,
bins=np.linspace(min(x_rand), max(x_rand),
25),
normed=True,
alpha=alpha_hist)
ax.plot(x_rand,
pdf_fitted,
'-',
color=color_line,
linewidth=3,
label='D = ' + str(D) + '\nvarQ = ' + str(variance))
ax.set_title('Normal fit')
legend = ax.legend(loc='left', shadow=True, fontsize=20)
print 'NORM', mean, variance
extra = ''
if 'release' in filename:
extra = '_release-max'
write_row(
outfolder + '/' + label + '_' + name + '_tnorm_original_fit' + extra +
'.dat', [
str(x_rand[i]) + '\t' + str(pdf_fitted[i])
for i in range(len(x_rand))
])
write_row(
outfolder + '/' + label + '_' + name + '_tnorm_mean_centered_fit' +
extra + '.dat', [
str(x_rand[i] - mean) + '\t' + str(pdf_fitted[i])
for i in range(len(x_rand))
])
write_row(
outfolder + '/' + label + '_' + name + '_tnorm_peak_centered_fit' +
extra + '.dat', [
str(x_rand[i] - maxx) + '\t' + str(pdf_fitted[i])
for i in range(len(x_rand))
])
write_row(
outfolder + '/' + label + '_' + name + '_tnorm_mean_centered_fit' +
extra + 'sample' + '.dat', [
str(x_rand[i] - mean) + '\t' + str(pdf_fitted[i])
for i in range(len(x_rand))[0::filterparam]
])
write_row(
outfolder + '/' + label + '_' + name + '_tnorm_peak_centered_fit' +
extra + 'sample' + '.dat', [
str(x_rand[i] - maxx) + '\t' + str(pdf_fitted[i])
for i in range(len(x_rand))[0::filterparam]
])
write_row(
outfolder + '/' + label + '_' + name + '_tnorm_original_hist_' +
extra + '.dat', rand)
fout = open(statfile, 'a')
fout.write(label + '\t' + name + '\t' + str(D) + '\t' + str(mean) + '\t' +
str(variance) + '\n')
fout.close()
def fitLognormal(filename,
ax,
label='',
out_folder='',
name='',
cutoff=-sys.maxint,
writeout=True,
noise=False,
norm='no'):
rand = []
if 'log_p' in name:
rand = np.asarray([
math.exp(float(line.strip())) + noise for line in open(filename)
if float(line.strip()) > cutoff
])
elif 'log_Q' in name:
rand = np.asarray([
math.exp(float(line.strip().split('\t')[1]))
for line in open(filename) if len(line.strip().split('\t')) > 1
and float(line.strip().split('\t')[1]) > cutoff
])
elif noise:
rand = np.asarray([
float(line.strip()) + random.random() for line in open(filename)
if float(line.strip()) > cutoff
])
else:
rand = np.asarray([
float(line.strip()) + random.random() for line in open(filename)
if float(line.strip()) > cutoff
])
x_rand, p_rand = getDistribution(rand)
# histogram
nbins = 20
counts, bins, bars = ax.hist(rand,
normed=True,
bins=10**np.linspace(np.log10(min(x_rand)),
np.log10(max(x_rand)),
nbins),
log=True,
alpha=0.0,
cumulative=1)
ax.plot((bins[1:] + bins[:-1]) / 2,
counts,
's-',
color='royalblue',
alpha=0.0,
markersize=0,
linewidth=5)
bins = (bins[1:] + bins[:-1]) / 2
# fit and plot the powerlaw
print 'Fit and plot the lognormal...' + label
p0 = stats.lognorm._fitstart(rand)
p1 = stats.lognorm.fit(rand, p0[0], loc=p0[1], scale=p0[2])
param = stats.lognorm.fit(rand, p1[0], loc=p1[1], scale=p1[2])
ppdf_fitted = stats.lognorm.cdf(x_rand,
param[0],
loc=param[1],
scale=param[2])
mu = np.log(param[2])
sigma = param[0]
ax.set_xlabel(label, fontsize=20)
ax.set_ylabel('CDF of ' + label, fontsize=20)
cdf_fitted = stats.lognorm.cdf(x_rand,
param[0],
loc=param[1],
scale=param[2])
sk_results_norm = stats.ks_2samp(
cdf_fitted,
np.cumsum(p_rand)) # stats.ks_2samp(np.cumsum(p_rand), np.cumsu
print label, '\t', norm, '\t', sk_results_norm[0]
extra = ''
if 'release' in filename:
extra = '_release-max'
if writeout:
if not os.path.exists(out_folder):
os.makedirs(out_folder)
write_row(
out_folder + '/' + label + '_' + name + '_lognormal_pdf_' + norm +
extra + '.dat', [
str(x_rand[i]) + '\t' + str(ppdf_fitted[i])
for i in range(len(x_rand))
])
write_row(
out_folder + '/' + label + '_' + name + '_lognormal_hist_pdf_' +
str(nbins) + '_' + norm + extra + '.dat',
[str(bins[i]) + '\t' + str(counts[i]) for i in range(len(counts))])
return
def fitPowerLaw(filename,
ax,
label='',
out_folder='',
name='',
cutoff=-sys.maxint,
writeout=True,
noise=False,
distancefile=''):
rand = []
if 'log_p' in name:
rand = np.asarray([
math.exp(float(line.strip())) + noise for line in open(filename)
if float(line.strip()) > cutoff
])
elif 'log_Q' in name:
rand = np.asarray([
math.exp(float(line.strip().split('\t')[1]))
for line in open(filename) if len(line.strip().split('\t')) > 1
and float(line.strip().split('\t')[1]) > cutoff
])
elif noise:
rand = np.asarray([
float(line.strip()) + random.random() for line in open(filename)
if float(line.strip()) > cutoff
])
else:
rand = np.asarray([
float(line.strip()) + random.random() for line in open(filename)
if float(line.strip()) > cutoff
])
x_rand, p_rand = getDistribution(rand)
ax.set_title(label, fontsize=18)
# histogram
counts, bins, bars = ax.hist(rand,
normed=True,
bins=10**np.linspace(np.log10(min(x_rand)),
np.log10(max(x_rand)),
1000),
log=True,
alpha=0.0,
cumulative=1)
ax.plot((bins[1:] + bins[:-1]) / 2,
counts,
's-',
color='royalblue',
alpha=0.7,
markersize=0,
linewidth=5)
bins = (bins[1:] + bins[:-1]) / 2
ax.set_ylim([min(counts), 1.05 * max(counts)])
ax.set_xlim([min(x_rand), max(bins)])
# fit and plot the powerlaw
print 'Fit and plot the powerlaw...'
results = powerlaw.Fit(rand, xmin=min(x_rand), fit_method='KS')
alpha = results.power_law.alpha
D = results.power_law.KS()
parassms = results.power_law.plot_cdf(color='r',
ax=ax,
linestyle='-',
linewidth=3,
label='$\\alpha$= ' +
str(round(alpha, 2)) + ', $D$=' +
str(round(D, 2)))
# fit and plot the powerlaw
print 'Fit and plot the lognormal...' + label
p0 = stats.lognorm._fitstart(rand)
p1 = stats.lognorm.fit(rand, p0[0], loc=p0[1], scale=p0[2])
param = stats.lognorm.fit(rand, p1[0], loc=p1[1], scale=p1[2])
pdf_fitted = stats.lognorm.cdf(x_rand,
param[0],
loc=param[1],
scale=param[2])
ppdf_fitted = stats.lognorm.pdf(x_rand,
param[0],
loc=param[1],
scale=param[2])
mu = np.log(param[2])
sigma = param[0]
sk_results_norm = stats.ks_2samp(
pdf_fitted,
np.cumsum(p_rand)) # stats.ks_2samp(np.cumsum(p_rand), np.cumsu
ax.plot(x_rand,
pdf_fitted,
'k-',
linewidth=4,
label='Lognormal fit, $\\mu$=' + str(round(mu, 2)) +
'\n$\\sigma$=' + str(round(sigma, 2)) + ', $D$=' +
str(round(sk_results_norm[0], 2)))
print sk_results_norm, D
ax.set_xlabel(label, fontsize=20)
ax.set_ylabel('CDF of ' + label, fontsize=20)
extra = ''
if 'release' in filename:
extra = '_release-max'
if writeout:
if not os.path.exists(out_folder):
os.makedirs(out_folder)
xfit = parassms.lines[1].get_xdata()
yfit = parassms.lines[1].get_ydata()
write_row(
out_folder + '/' + label + '_' + name + '_powerlaw_hist_' + extra +
'.dat',
[str(bins[i]) + '\t' + str(counts[i]) for i in range(len(counts))])
write_row(
out_folder + '/' + label + '_' + name + '_powerlaw_fit_' + extra +
'.dat',
[str(xfit[i]) + '\t' + str(yfit[i]) for i in range(len(xfit))])
write_row(
out_folder + '/' + label + '_' + name + '_lognormal_' + extra +
'.dat', [
str(x_rand[i]) + '\t' + str(pdf_fitted[i])
for i in range(len(x_rand))
])
write_row(
out_folder + '/' + label + '_' + name + '_lognormal_pdf_' + extra +
'.dat', [
str(x_rand[i]) + '\t' + str(ppdf_fitted[i])
for i in range(len(x_rand))
])
f_Ddata = open(distancefile, 'a')
f_Ddata.write(label + '\t' + str(D) + '\t' + str(sk_results_norm[0]) +
'\n')
f_Ddata.close()
return sk_results_norm[0], D
def get_imapct_distr():
''' ---------------------------------------------- '''
''' MOVIE YO '''
professions = [('director', 'k'), ('producer', 'b'), ('writer', 'r'),
('composer', 'g'), ('art-director', 'y')]
num_of_bins = 20
title_font = 25
seaborn.set_style('white')
f, ax = plt.subplots(2, 3, figsize=(25, 15))
st = f.suptitle("IMDb normalized impact distributions",
fontsize=title_font)
FOLDER = 'ProcessedDataNormalized'
for (label, color) in professions:
num_car = str(
int(
round(
len(
os.listdir('Data/Film/film-' + label +
'-simple-careers')) / 1000.0))) + 'k'
file_avg = FOLDER + '/1_impact_distributions/film_average_ratings_dist_' + label + '.dat'
file_cnt = FOLDER + '/1_impact_distributions/film_rating_counts_dist_' + label + '.dat'
file_mets = FOLDER + '/1_impact_distributions/film_metascores_dist_' + label + '.dat'
file_crit = FOLDER + '/1_impact_distributions/film_critic_review_dist_' + label + '.dat'
file_user = FOLDER + '/1_impact_distributions/film_user_review_dist_' + label + '.dat'
average_ratings = np.asarray(
[round(float(line.strip()), 2) for line in open(file_avg)])
rating_counts = [
round(float(line.strip()), 2) for line in open(file_cnt)
]
metascores = [
round(float(line.strip()), 1) for line in open(file_mets)
]
critic_review = [
round(float(line.strip()), 2) for line in open(file_crit)
]
user_review = [
round(float(line.strip()), 2) for line in open(file_user)
]
# plot avg ratings
x_average_ratings, p_average_ratings = getDistribution(
average_ratings, True)
bx_average_ratings, bp_average_ratings, bperr_average_ratings = getBinnedDistribution(
x_average_ratings, p_average_ratings, num_of_bins)
ax[0, 0].set_title('IMDb - average rating', fontsize=20)
ax[0, 0].plot(x_average_ratings,
p_average_ratings,
color,
marker='o',
alpha=0.1,
linewidth=0,
label=label + ', ' + str(num_car))
ax[0, 0].errorbar(
(bx_average_ratings[1:] + bx_average_ratings[:-1]) / 2,
bp_average_ratings,
yerr=bperr_average_ratings,
fmt=color + '-',
linewidth=2)
# plot rating counts
x_rating_counts, p_rating_counts = getDistribution(rating_counts, True)
bx_rating_counts, bp_rating_counts, bperr_rating_counts = getBinnedDistribution(
x_rating_counts, p_rating_counts, num_of_bins)
ax[0, 1].set_title('IMDb - rating count', fontsize=20)
ax[0, 1].set_xscale('log')
ax[0, 1].set_yscale('log')
ax[0, 1].plot(x_rating_counts,
p_rating_counts,
color + 'o',
alpha=0.8,
label=label) # + ', ' + str(num_wr))
#ax[0,1].errorbar((bx_rating_counts[1:] + bx_rating_counts[:-1])/2, bp_rating_counts, yerr=bperr_rating_counts, fmt='b-', linewidth = 2)
# plot metascores
x_metascores, p_metascores = getDistribution(metascores, True)
bx_metascores, bp_metascores, bperr_metascores = getBinnedDistribution(
x_metascores, p_metascores, num_of_bins)
ax[0, 2].set_title('IMDb - metascores', fontsize=20)
ax[0, 2].plot(x_metascores,
p_metascores,
color + 'o',
alpha=0.2,
label=label) # + ', ' + str(len(metascores)))
ax[0, 2].errorbar((bx_metascores[1:] + bx_metascores[:-1]) / 2,
bp_metascores,
yerr=bperr_metascores,
fmt=color + '-',
linewidth=2)
# plot critic review count
x_critic_review, p_critic_review = getDistribution(critic_review, True)
ax[1, 0].set_title('IMDb - critic_review', fontsize=20)
ax[1, 0].set_xscale('log')
ax[1, 0].set_yscale('log')
ax[1, 0].plot(x_critic_review,
p_critic_review,
color + 'o',
alpha=0.8,
label=label) #+ ', ' + str(len(critic_review)))
# plot user review count
x_user_review, p_user_review = getDistribution(user_review, True)
ax[1, 1].set_title('IMDb - user_review', fontsize=20)
ax[1, 1].set_xscale('log')
ax[1, 1].set_yscale('log')
ax[1, 1].plot(x_user_review,
p_user_review,
color + 'o',
alpha=0.8,
label=label) # + ', ' + str(len(user_review)))
''' ---------------------------------------------- '''
''' MOVIE YO '''
genres = [('electro', 'k'), ('pop', 'b')]
for (genre, color) in genres:
num_mus = str(
int(
round(
len(
os.listdir('Data/Music/music-' + genre +
'-simple-careers')) / 1000.0))) + 'k'
file_music = FOLDER + '/1_impact_distributions/music_rating_counts_dist_' + genre + '.dat'
average_ratings = np.asarray(
[round(float(line.strip())) for line in open(file_music)])
x_rating_counts, p_rating_counts = getDistribution(
average_ratings, True)
print len(average_ratings)
ax[1, 2].set_title('Music - playcount', fontsize=20)
ax[1, 2].set_xscale('log')
ax[1, 2].set_yscale('log')
ax[1, 2].plot(x_rating_counts,
p_rating_counts,
color + 'o',
alpha=0.2,
label=genre + ', ' + num_mus)
align_plot(ax)
plt.savefig('impact_distributions_normalized.png')
plt.close()
def get_career_length():
title_font = 25
num_of_bins = 20
seaborn.set_style('white')
f, ax = plt.subplots(1, 2, figsize=(22, 9))
st = f.suptitle("Career length distributions", fontsize=title_font)
professions = [
('director', 'k'),
('producer', 'b'),
('writer', 'r'),
('composer', 'g'),
('art-director', 'y'),
]
for (label, color) in professions[0:1]:
career_length = [
float(line.strip()) for line in
open('ProcessedData/5_career_length/film_career_length_' + label +
'.dat')
]
xcareer_length, pcareer_length = getDistribution(career_length)
#ax[0].plot(xcareer_length, pcareer_length, color, marker = 'o', alpha = 0.3, linewidth = 0, label = label+ ', ')
fitPowerLaw([c for c in career_length if c > 10], ax[0], label)
#results = powerlaw.Fit(career_length, xmin = min(xcareer_length), fit_method = 'KS')
# alpha = results.power_law.alpha
#D = results.power_law.KS()
#results.plot_pdf(color=color, ax = ax[0], linestyle='-', linewidth=0, marker = 'o', alpha = 0.5)
# results.power_law.plot_pdf(color=color, ax = ax[0], linestyle='-', linewidth=3, alpha = 0.9, label ='$\\alpha$= ' + str(round(alpha,2)) + ', $D$='+str(round(D, 2) ))
ax[0].set_title('Length of director careers', fontsize=18)
ax[1].set_title('Length of DJ careers', fontsize=18)
professions = [('pop', 'k'), ('electro', 'b')]
for (label, color) in professions[1:2]:
career_length = [
float(line.strip()) for line in
open('ProcessedData/5_career_length/music_career_length_' + label +
'.dat')
]
xcareer_length, pcareer_length = getDistribution(career_length)
fitPowerLaw([c for c in career_length if c > 10], ax[1], label)
'''
results = powerlaw.Fit(career_length, xmin = min(xcareer_length), fit_method = 'KS')
alpha = results.power_law.alpha
D = results.power_law.KS()
results.plot_pdf(color=color, ax = ax[1], linestyle = '-', linewidth = 0, marker = 'o', alpha = 0.5)
results.power_law.plot_pdf(color=color, ax = ax[1], linestyle='-', linewidth=3, alpha = 0.9, label ='$\\alpha$= ' + str(round(alpha,2)) + ', $D$='+str(round(D, 2) ))
'''
align_plot1D(ax)
plt.savefig('career_length.png')
plt.close()